It has been demonstrated repeatedly that combining multiple types of image features improves the performance of learning-based classification and regression. However, no tools exist to facilitate the creation of large pools of feature extractors by extended teams of contributors. The MASH project aims at creating such tools. It is organized around the development of a collaborative web platform...

Randomness is crucial to computer science, both in theory and applications. In complexity theory, randomness augments computers to offer more powerful models. In cryptography, randomness is essential for seed generation, where the computational model used is generally probabilistic. However, ideal randomness, which is usually assumed to be available in computer science theory and applications, ...

Interactive Learning of Relation Extractors with Weak Supervision

This lecture is about randomness extractors. Extractors are functions that map samples from a non-uniform distribution to samples that are close to being uniformly distributed. The length of the output will in general be smaller than the length of the input of the extractor. The input distribution of the extractor is called the source. A source is a random variable which maps text values to bit...

Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, ...

We establish tight bounds on the amount on nonuniformity that is necessary for extracting a string with randomness rate 1 from a single source of randomness with lower randomness rate. More precisely, as instantiations of more general results, we show that while O(1) amount of advice regarding the source is not enough for extracting a string with randomness rate 1 from a source string with cons...

BACKGROUND As we are witnessing a great interest in identifying and extracting chemical entities in academic articles, many approaches have been proposed to solve this problem. In this work we describe a probabilistic framework that allows for the output of multiple information extraction systems to be combined in a systematic way. The identified entities are assigned a probability score that r...